© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 18671
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sum" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coni
    -0.17
    ough
    -0.17
    Ĩ
    -0.15
    amber
    -0.15
    .za
    -0.15
    enburg
    -0.15
    ustry
    -0.14
    Plain
    -0.14
    ãĥĹãĥ¬
    -0.14
    xdb
    -0.14
    POSITIVE LOGITS
    ming
    0.33
    ption
    0.32
    pt
    0.30
    pter
    0.29
    maries
    0.27
    ptions
    0.27
    mons
    0.26
    mers
    0.26
    atra
    0.24
    ma
    0.24
    Activations Density 0.020%

    No Known Activations